RichardErkhov commited on
Commit
7f3d7ea
1 Parent(s): 719d1e5

uploaded model

Browse files
Files changed (1) hide show
  1. config.json +44 -0
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Qwen2-0.5B-DPO",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 896,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4864,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 24,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 14,
17
+ "num_hidden_layers": 24,
18
+ "num_key_value_heads": 2,
19
+ "quantization_config": {
20
+ "_load_in_4bit": false,
21
+ "_load_in_8bit": true,
22
+ "bnb_4bit_compute_dtype": "float32",
23
+ "bnb_4bit_quant_storage": "uint8",
24
+ "bnb_4bit_quant_type": "fp4",
25
+ "bnb_4bit_use_double_quant": false,
26
+ "llm_int8_enable_fp32_cpu_offload": false,
27
+ "llm_int8_has_fp16_weight": false,
28
+ "llm_int8_skip_modules": null,
29
+ "llm_int8_threshold": 6.0,
30
+ "load_in_4bit": false,
31
+ "load_in_8bit": true,
32
+ "quant_method": "bitsandbytes"
33
+ },
34
+ "rms_norm_eps": 1e-06,
35
+ "rope_scaling": null,
36
+ "rope_theta": 1000000.0,
37
+ "sliding_window": null,
38
+ "tie_word_embeddings": true,
39
+ "torch_dtype": "float16",
40
+ "transformers_version": "4.44.2",
41
+ "use_cache": true,
42
+ "use_sliding_window": false,
43
+ "vocab_size": 151936
44
+ }